no code implementations • 24 Jan 2025 • Zili Liu, Hao Chen, Lei Bai, Wenyuan Li, Zhengxia Zou, Zhenwei Shi
Obtaining accurate weather forecasts at station locations is a critical challenge due to systematic biases arising from the mismatch between multi-scale, continuous atmospheric characteristic and their discrete, gridded representations.
no code implementations • 20 Jan 2025 • Songru Yang, Zili Liu, Zhenwei Shi, Zhengxia Zou
Global Station Weather Forecasting (GSWF), a prominent meteorological research area, is pivotal in providing timely localized weather predictions.
1 code implementation • 12 Jan 2025 • Keyan Chen, Jiafan Zhang, Chenyang Liu, Zhengxia Zou, Zhenwei Shi
Referring remote sensing image segmentation is crucial for achieving fine-grained visual understanding through free-format textual input, enabling enhanced scene and object extraction in remote sensing applications.
no code implementations • 1 Jan 2025 • Chenyang Liu, Keyan Chen, Rui Zhao, Zhengxia Zou, Zhenwei Shi
On the previous benchmark dataset, Text2Earth outperforms previous models with an improvement of +26. 23 FID and +20. 95% Zero-shot Cls-OA metric. Our project page is \url{https://chen-yang-liu. github. io/Text2Earth}
no code implementations • 8 Dec 2024 • Zipeng Qi, Hao Chen, Haotian Zhang, Zhengxia Zou, Zhenwei Shi
In this paper, we propose a novel semantic splatting approach based on Gaussian Splatting to achieve efficient and low-latency.
1 code implementation • 3 Dec 2024 • Chenyang Liu, Jiafan Zhang, Keyan Chen, Man Wang, Zhengxia Zou, Zhenwei Shi
This survey fills a critical gap in the literature by providing an integrated overview of RSTVLM, offering a foundation for further advancements in remote sensing temporal image understanding.
no code implementations • 20 Aug 2024 • Zili Liu, Hao Chen, Lei Bai, Wenyuan Li, Wanli Ouyang, Zhengxia Zou, Zhenwei Shi
In an era of frequent extreme weather and global warming, obtaining precise, fine-grained near-surface weather forecasts is increasingly essential for human activities.
1 code implementation • 22 Jul 2024 • Kaiyu Li, Jiawei Jiang, Andrea Codegoni, Chengxi Han, Yupeng Deng, Keyan Chen, Zhuo Zheng, Hao Chen, Zhengxia Zou, Zhenwei Shi, Sheng Fang, Deyu Meng, Zhi Wang, Xiangyong Cao
We present Open-CD, a change detection toolbox that contains a rich set of change detection methods as well as related components and modules.
1 code implementation • 15 Jun 2024 • Chenyao Zhou, Haotian Zhang, Han Guo, Zhengxia Zou, Zhenwei Shi
Recently some multi-task learning based semantic change detection methods have been proposed to decompose the task into semantic segmentation and binary change detection subtasks.
3 code implementations • 6 Jun 2024 • Haotian Zhang, Keyan Chen, Chenyang Liu, Hao Chen, Zhengxia Zou, Zhenwei Shi
Specifically, the Scaled Residual ConvMamba (SRCM) block is proposed to utilize the ability of Mamba to extract global features and convolution to enhance the local details, to alleviate the issue that current Mamba-based methods lack detailed clues and are difficult to achieve fine detection in dense prediction tasks.
Ranked #4 on
Change Detection
on LEVIR+
no code implementations • 23 May 2024 • Zipeng Qi, Chenyang Liu, Zili Liu, Hao Chen, Yongchang Wu, Zhengxia Zou, Zhenwei Sh
Subsequently, we introduce SAM features via a transformer into the INF of the scene, supplementing the semantic information.
no code implementations • 22 May 2024 • Zhiping Yu, Chenyang Liu, Liqin Liu, Zhenwei Shi, Zhengxia Zou
To achieve unbounded and arbitrary-sized image generation, we design a novel noise sampling strategy for denoising diffusion models by analyzing the generation conditions and initial noise.
1 code implementation • 29 Apr 2024 • Chenyang Liu, Keyan Chen, Bowen Chen, Haotian Zhang, Zhengxia Zou, Zhenwei Shi
In terms of efficient temporal modeling, considering the potential correlation between the temporal scanning characteristics of Mamba and the temporality of the RSICC, we propose the Temporal-Traversing SSM (TT-SSM), which scans bi-temporal features in a temporal cross-wise manner, enhancing the model's temporal understanding and information interaction.
1 code implementation • 28 Mar 2024 • Chenyang Liu, Keyan Chen, Haotian Zhang, Zipeng Qi, Zhengxia Zou, Zhenwei Shi
Remote sensing satellite imagery offers a unique perspective for monitoring these changes, leading to the emergence of remote sensing image change interpretation (RSICI) as a significant research focus.
3 code implementations • 28 Mar 2024 • Keyan Chen, Bowen Chen, Chenyang Liu, Wenyuan Li, Zhengxia Zou, Zhenwei Shi
Remote sensing image classification forms the foundation of various understanding tasks, serving a crucial function in remote sensing image interpretation.
1 code implementation • IEEE Transactions on Geoscience and Remote Sensing 2024 • Haotian Zhang, Hao Chen, Chenyao Zhou, Keyan Chen, Chenyang Liu, Zhengxia Zou, Zhenwei Shi
Despite the success of deep learning-based change detection (CD) methods, their existing insufficiency in temporal (channel and spatial) and multiscale alignment has rendered them insufficient capability in mitigating external factors (illumination changes and perspective differences) arising from different imaging conditions during CD.
Ranked #2 on
Change Detection
on WHU-CD
1 code implementation • 22 Jan 2024 • Zili Liu, Hao Chen, Lei Bai, Wenyuan Li, Keyan Chen, Zhengyi Wang, Wanli Ouyang, Zhengxia Zou, Zhenwei Shi
In this paper, we extend meteorological downscaling to arbitrary scattered station scales, establish a brand new benchmark and dataset, and retrieve meteorological states at any given station location from a coarse-resolution meteorological field.
no code implementations • 17 Jan 2024 • Zili Liu, Hao Chen, Wenyuan Li, Keyan Chen, Zipeng Qi, Chenyang Liu, Zhengxia Zou, Zhenwei Shi
This paper is the first to consider the impact of label noise on the detection of clouds and snow in remote sensing images.
1 code implementation • 4 Jan 2024 • Wenyuan Li, Zili Liu, Keyan Chen, Hao Chen, Shunlin Liang, Zhengxia Zou, Zhenwei Shi
Next, we construct hyper-networks based on deep learning methods to directly learn weather patterns from a large amount of meteorological data.
3 code implementations • 23 Dec 2023 • Keyan Chen, Chengyang Liu, Wenyuan Li, Zili Liu, Hao Chen, Haotian Zhang, Zhengxia Zou, Zhenwei Shi
Change detection, a prominent research area in remote sensing, is pivotal in observing and analyzing surface transformations.
Ranked #9 on
Change Detection
on LEVIR-CD
no code implementations • 23 Dec 2023 • Chenyang Liu, Keyan Chen, Zipeng Qi, Haotian Zhang, Zhengxia Zou, Zhenwei Shi
The existing methods for Remote Sensing Image Change Captioning (RSICC) perform well in simple scenes but exhibit poorer performance in complex scenes.
no code implementations • 22 Oct 2023 • Zhiqian Lin, Jiangke Lin, Lincheng Li, Yi Yuan, Zhengxia Zou
In our method, an affine transformation matrix is learned from the affine convolution layer for each spatial location of the feature maps.
no code implementations • 8 Oct 2023 • Rusheng Zhang, Depu Meng, Shengyin Shen, Zhengxia Zou, Houqiang Li, Henry X. Liu
As vehicular communication and networking technologies continue to advance, infrastructure-based roadside perception emerges as a pivotal tool for connected automated vehicle (CAV) applications.
no code implementations • 11 Aug 2023 • Yapeng Meng, Songru Yang, Xu Hu, Rui Zhao, Lincheng Li, Zhenwei Shi, Zhengxia Zou
Our method can also be flexibly extended to real-time video face editing.
1 code implementation • 17 Jul 2023 • Jianqi Chen, Yilan Zhang, Zhengxia Zou, Keyan Chen, Zhenwei Shi
Initially, we employ a pretrained vision-language model (VLM) to generate descriptions for the composite image.
no code implementations • 29 Jun 2023 • Rusheng Zhang, Depu Meng, Lance Bassett, Shengyin Shen, Zhengxia Zou, Henry X. Liu
Our approach was rigorously tested at two key intersections in Michigan, USA: the Mcity intersection and the State St./Ellsworth Rd roundabout.
1 code implementation • 28 Jun 2023 • Keyan Chen, Chenyang Liu, Hao Chen, Haotian Zhang, Wenyuan Li, Zhengxia Zou, Zhenwei Shi
We also propose several ongoing derivatives for instance segmentation tasks, drawing on recent advancements within the SAM community, and compare their performance with RSPrompter.
1 code implementation • 24 May 2023 • Hao Chen, Haotian Zhang, Keyan Chen, Chenyao Zhou, Song Chen, Zhengxia Zou, Zhenwei Shi
Toward continuous cross-resolution CD, we propose scale-invariant learning to enforce the model consistently predicting HR results given synthesized samples of varying resolution differences.
1 code implementation • 14 May 2023 • Jianqi Chen, Hao Chen, Keyan Chen, Yilan Zhang, Zhengxia Zou, Zhenwei Shi
Many existing adversarial attacks generate $L_p$-norm perturbations on image RGB space.
no code implementations • 15 Mar 2023 • Zipeng Qi, Hao Chen, Chenyang Liu, Zhenwei Shi, Zhengxia Zou
In the first stage, we optimize a neural field to encode the color and 3D structure of the remote sensing scene based on multi-view images.
1 code implementation • 3 Mar 2023 • Jianqi Chen, Yilan Zhang, Zhengxia Zou, Keyan Chen, Zhenwei Shi
High-resolution (HR) image harmonization is of great significance in real-world applications such as image synthesis and image editing.
Ranked #8 on
Image Harmonization
on iHarmony4
no code implementations • CVPR 2023 • Rui Zhao, Wei Li, Zhipeng Hu, Lincheng Li, Zhengxia Zou, Zhenwei Shi, Changjie Fan
In our method, taking the power of large-scale pre-trained multi-modal CLIP and neural rendering, T2P searches both continuous facial parameters and discrete facial parameters in a unified framework.
1 code implementation • 1 Mar 2023 • Chenyang Liu, Jiajun Yang, Zipeng Qi, Zhengxia Zou, Zhenwei Shi
To sufficiently utilize the extracted multi-scale features for captioning, we propose a scale-aware reinforcement (SR) module and combine it with the Transformer decoding layer to progressively utilize the features from different PDP layers.
1 code implementation • 16 Feb 2023 • Keyan Chen, Wenyuan Li, Sen Lei, Jianqi Chen, XiaoLong Jiang, Zhengxia Zou, Zhenwei Shi
Despite its fruitful applications in remote sensing, image super-resolution is troublesome to train and deploy as it handles different resolution magnifications with separate models.
no code implementations • CVPR 2023 • Yongqiang Zhang, Zhipeng Hu, Haoqian Wu, Minda Zhao, Lincheng Li, Zhengxia Zou, Changjie Fan
In this paper, we argue that this limited accuracy is due to the bias of their volume rendering strategies, especially when the viewing direction is close to be tangent to the surface.
no code implementations • 20 Jun 2022 • Zhengxia Zou, Rusheng Zhang, Shengyin Shen, Gaurav Pandey, Punarjay Chakravarty, Armin Parchami, Henry X. Liu
We propose a novel and pragmatic framework for traffic scene perception with roadside cameras.
1 code implementation • 18 May 2022 • Yongchang Wu, Zhengxia Zou, Zhenwei Shi
In this paper, we propose a novel remote sensing view synthesis method by leveraging the recent advances in implicit neural representations.
1 code implementation • Remote Sens. 2021 • Keyan Chen, Zhengxia Zou, Zhenwei Shi
Deep learning methods have achieved considerable progress in remote sensing image building extraction.
Building change detection for remote sensing images
Extracting Buildings In Remote Sensing Images
no code implementations • 24 Mar 2021 • Dan Wang, Xinrui Cui, Xun Chen, Zhengxia Zou, Tianyang Shi, Septimiu Salcudean, Z. Jane Wang, Rabab Ward
Unlike previous CNN-based methods using a separate design, we unify the feature extraction and view fusion in a single Transformer network.
Ranked #7 on
3D Reconstruction
on ShapeNet
1 code implementation • 1 Mar 2021 • Yinglin Duan, Tianyang Shi, Zhengxia Zou, Yenan Lin, Zhehui Qian, Bohan Zhang, Yi Yuan
Motion completion is a challenging and long-discussed problem, which is of great significance in film and game applications.
Ranked #2 on
Motion Synthesis
on LaFAN1
1 code implementation • 4 Feb 2021 • Jiangke Lin, Yi Yuan, Zhengxia Zou
To tackle these problems, we propose 1) a low-cost facial texture acquisition method, 2) a shape transfer algorithm that can transform the shape of a 3DMM mesh to games, and 3) a new pipeline for training 3D game face reconstruction networks.
no code implementations • ICCV 2021 • Dan Wang, Xinrui Cui, Xun Chen, Zhengxia Zou, Tianyang Shi, Septimiu Salcudean, Z. Jane Wang, Rabab Ward
Unlike previous CNN-based methods using a separate design, we unify the feature extraction and view fusion in a single Transformer network.
1 code implementation • 31 Dec 2020 • Zhengxia Zou, Tianyang Shi, Yi Yuan, Zhenwei Shi
This paper studies an interesting question that whether a deep CNN can be trained to recover the depth behind an autostereogram and understand its content.
4 code implementations • CVPR 2021 • Zhengxia Zou, Tianyang Shi, Shuang Qiu, Yi Yuan, Zhenwei Shi
Different from previous image-to-image translation methods that formulate the translation as pixel-wise prediction, we deal with such an artistic creation process in a vectorized environment and produce a sequence of physically meaningful stroke parameters that can be further used for rendering.
4 code implementations • 22 Oct 2020 • Zhengxia Zou
This paper proposes a vision-based method for video sky replacement and harmonization, which can automatically generate realistic and dramatic sky backgrounds in videos with controllable styles.
no code implementations • 27 Sep 2020 • Yinglin Duan, Tianyang Shi, Zhengxia Zou, Jia Qin, Yifei Zhao, Yi Yuan, Jie Hou, Xiang Wen, Changjie Fan
Previous works of this topic consider music-to-dance as a supervised motion generation problem based on time-series data.
1 code implementation • 17 Aug 2020 • Tianyang Shi, Zhengxia Zou, Xinhui Song, Zheng Song, Changjian Gu, Changjie Fan, Yi Yuan
Besides, the neural network based renderer used in previous methods is also difficult to be extended to multi-view rendering cases.
no code implementations • 17 Aug 2020 • Tianyang Shi, Zhengxia Zou, Yi Yuan, Changjie Fan
With the rapid development of Role-Playing Games (RPGs), players are now allowed to edit the facial appearance of their in-game characters with their preferences rather than using default templates.
no code implementations • CVPR 2020 • Zhengxia Zou, Sen Lei, Tianyang Shi, Zhenwei Shi, Jieping Ye
Considering the layer separating ambiguity that given a single mixed input, there could be an infinite number of possible solutions, we introduce a "Separation-Critic" - a discriminative network which is trained to identify whether the output layers are well-separated and thus further improves the layer separation.
no code implementations • ICCV 2019 • Zhengxia Zou, Wenyuan Li, Tianyang Shi, Zhenwei Shi, Jieping Ye
The detection and removal of cloud in remote sensing images are essential for earth observation applications.
no code implementations • 26 Sep 2019 • Huapeng Wu, Zhengxia Zou, Jie Gui, Wen-Jun Zeng, Jieping Ye, Jun Zhang, Hongyi Liu, Zhihui Wei
In this paper, we make a thorough investigation on the attention mechanisms in a SR model and shed light on how simple and effective improvements on these ideas improve the state-of-the-arts.
no code implementations • ICCV 2019 • Tianyang Shi, Yi Yuan, Changjie Fan, Zhengxia Zou, Zhenwei Shi, Yong liu
Character customization system is an important component in Role-Playing Games (RPGs), where players are allowed to edit the facial appearance of their in-game characters with their own preferences rather than using default templates.
1 code implementation • 13 May 2019 • Zhengxia Zou, Keyan Chen, Zhenwei Shi, Yuhong Guo, Jieping Ye
Object detection, as of one the most fundamental and challenging problems in computer vision, has received great attention in recent years.